用少量真实数据实现无人机与赛车的高效自适应控制
Sym2Real: Symbolic Dynamics with Residual Learning for Data-Efficient Adaptive Control
- 先在无噪声仿真中通过符号回归提取动力学方程
- 仅用约10条真实轨迹即可实现鲁棒控制
- 适合缺乏专家经验的机器人快速部署场景
我们提出Sym2Real，一个完全数据驱动的低层控制器高效自适应框架。尽管符号回归具有数据效率优势，但其在真实控制中的应用受限于对测量噪声敏感，直接在真实数据上拟合会导致模型退化。Sym2Real通过两点解决此问题：1）首先在低保真度仿真中学习，利用无噪声轨迹使符号回归识别底层动力学；2）仅使用少量真实世界数据进行目标残差适应，弥合仿真到现实的差距。仅需约10条轨迹，即在真实世界中实现无人机和赛车的鲁棒控制，无需专家知识或仿真调参。在两个平台上的实验验证表明，该方法在6个分布外的仿真-仿真场景中表现一致，并成功实现了5种真实环境下的仿真到现实迁移。
原文摘要 · Abstract (English)
We present Sym2Real, a fully data-driven framework for highly data-efficient adaptation of low-level controllers. Although symbolic regression is data-efficient, its role in real-world control has been limited due to its sensitivity to measurement noise, which corrupts the equations and leads to model degradation when fitted directly on real-world data. Sym2Real addresses this limitation by 1) learning first from low-fidelity simulation, where noise-free trajectories allow symbolic regression to identify the underlying dynamics, and 2) using a small amount of real-world data for targeted residual adaptation to bridge the sim-to-real gap. Using only about 10 trajectories, we achieve robust control of both a quadrotor and a racecar in the real world, without expert knowledge or simulation tuning. Through experimental validation on both platforms, we demonstrate consistent data-efficient adaptation across 6 out-of-distribution sim2sim scenarios and successful sim2real transfer across 5 real-world conditions. More information can be found at http://generalroboticslab.com/Sym2Real
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。